mlsanityData to 14 Oct 2026

A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction

arXiv 2606.12673 ↗First posted 10 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Cross-domain graph anomaly detection (GAD) aims to identify abnormal nodes in unseen target graphs, showing strong potential in real-world applications with heterogeneous graph data. However, existing methods often depend on dataset-specific feature semantics and structural patterns, which limits their ability to generalize across different domains. To address this challenge, we propose AlignGAD, a zero-shot generalized graph anomaly detection framework. Our framework is built upon three key components: a Global Unification Module that aligns heterogeneous node features and normalizes graph signals in the spectral domain; a Clustering Module that constructs cluster-aware graph views to capture group-level abnormal patterns; and a Node Discrepancy Scoring Module that measures reconstruction discrepancy and aggregates anomaly evidence from different graph views. Experiments on multiple real-world datasets demonstrate the effectiveness of AlignGAD under the zero-shot GAD setting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 30 references that are in the map. First posted on arXiv 10 Jun 2026.

Builds on

18 of 30 references.

References · 18

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  4. 2022Rethinking Graph Neural Networks for Anomaly Detectioncited by 187
  5. 2021Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learningcited by 177
  6. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  7. 2020AnomalyDAE: Dual autoencoder for anomaly detection on attributed networkscited by 82
  8. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  9. 2021Boost then Convolve: Gradient Boosting Meets Graph Neural Networkscited by 44
  10. 2023Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detectioncited by 43
  11. 2024Alleviating Structural Distribution Shift in Graph Anomaly Detectioncited by 32
  12. 2022Cross-Domain Graph Anomaly Detection via Anomaly-aware Contrastive Alignmentcited by 31
6 more
  1. 2024Zero-shot Generalist Graph Anomaly Detection with Unified Neighborhood Promptscited by 28
  2. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  3. 2022A Survey of Graph-based Deep Learning for Anomaly Detection in Distributed Systemscited by 20
  4. 2023Correlation-aware Spatial-Temporal Graph Learning for Multivariate Time-series Anomaly Detectioncited by 18
  5. 2024Counterfactual Data Augmentation with Denoising Diffusion for Graph Anomaly Detectioncited by 7
  6. 2026GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detectioncited by 3

Built on by

Not cited yet.